Background: In brain–computer interfaces (BCIs), transformer-based models have found extensive application in motor imagery (MI)-based EEG signal recognition. However, for subject-independent EEG recognition, these models face challenges: low sensitivity to spatial dynamics of neural activity and difficulty balancing high temporal resolution features with manageable computational complexity. The overarching objective is to address these critical issues. Methods: We introduce Mirror Contrastive Learning with Sliding Window Transformer (MCL-SWT). Inspired by left/right hand motor imagery inducing event-related desynchronization (ERD) in the contralateral sensorimotor cortex, we develop a mirror contrastive loss function. It segregates feature spaces of EEG signals from contralateral ERD locations while curtailing variability in signals sharing similar ERD locations. The Sliding Window Transformer computes self-attention scores over high temporal resolution features, enabling efficient capture of global temporal dependencies. Results: Evaluated on benchmark datasets for subject-independent MI EEG recognition, MCL-SWT achieves classification accuracies of 66.48% and 75.62%, outperforming State-of-the-Art models by 2.82% and 2.17%, respectively. Ablation studies validate the efficacy of both the mirror contrastive loss and sliding window mechanism. Conclusions: These findings underscore MCL-SWT’s potential as a robust, interpretable framework for subject-independent EEG recognition. By addressing existing challenges, MCL-SWT could significantly advance BCI technology development.

The presence of random fissures significantly alters the mechanical properties and failure mechanisms of rocks. To systematically investigate the impact of fissures on the failure behavior of sandstone, a multivariable random fissure numerical model was developed based on the Weibull distribution probability density function, in combination with a random fissure generation algorithm and cohesive element embedding method. This study primarily focuses on analyzing the influence of fissure ratio (R), fissure dip angle interval (A), fissure length interval (L), and fissure width interval (W) on the sandstone failure process. The results show that the failure modes change with variations in R, A, L, and W, specifically manifested as the formation of “X”-shaped, “Y”-shaped, or inverted “Y”-shaped primary cracks; the increase in fissure ratio significantly reduces both peak stress and total damage dissipated energy (ALLDMD), and promotes the propagation of tensile cracks; the increase in L leads to more complex failure patterns, but its effect on peak stress and peak strain fluctuates non-linearly, the ALLDMD remains insensitive to this change, while the number of tensile cracks decreases as L increases; conversely, an increase in W results in a failure mode characterized by a single crack path, the peak stress first increases and then decreases, and the ALLDMD exhibits an “N”-shaped fluctuation, though the overall variation is limited.

Based on the huge volumes of user check-in data in LBSNs, users’ intrinsic mobility patterns can be well explored, which is fundamental for predicting where a user will visit next given his/her historical check-in records. As there are various types of nodes and interactions in LBSNs, they can be treated as Heterogeneous Information Network (HIN) where multiple semantic meta-paths can be extracted. Inspired by the recent success of meta-path context based embedding techniques in HIN, in this paper, we design a deep neural network framework leveraging various meta-path contexts for fine-grained user location prediction. Experimental results based on two real-world LBSN datasets demonstrate the best effectiveness of the proposed approach using various evaluation metrics than others.